Enhanced Heart Disease Prediction Using Advanced Classifiers and Ensemble Learning Techniques

Heart disease is a major worldwide health concern, highlighting the importance of accurate and quick diagnosis. This study looks at machine learning-based prediction models for heart disease identification. Eight algorithms, including support vector machines, extreme gradient boosting, and random forests, were evaluated for accuracy, precision, recall, and ROC-AUC scores. Among them, the XGB model demonstrated outstanding performance, achieving a remarkable 97.88% accuracy and excelling in both sensitivity and specificity. In this study, we found that ensemble techniques can really handle complex datasets well, especially when we adjust hyperparameters to deal with imbalanced data. These results open up promising opportunities to use machine learning in hospitals for diagnosing and treating heart disease. This could lead to more accurate and effective outcomes. The result would be better patient care, which would lower healthcare costs. It might improve patient outcomes and increase economic efficiency for the whole health care system. These findings could also help develop better treatments and preventions for heart disease.